论文部分内容阅读
对光纤网络中的离群异常数据准确检测可实现网络故障诊断排除。针对目前光纤网络离群异常数据散布性强,检测准确度不高的问题,提出一种基于鉴频响应谱峰搜索的光纤网络中离群异常数据检测算法。首先构建光纤网络离群异常数据片选信号的特征分布幅频响应曲线,分析离散异常数据的超线性混沌特性,其次提取离群异常数据的鉴频响应特征,采用自适应谱峰搜索方法实现离群异常数据的聚集性检测。最后进行仿真测试,结果表明,采用本文方法进行光纤网络中的离群异常数据检测的准确性好,抗干扰能力较强。
Accurate detection of outlier anomalies in optical fiber networks can eliminate network troubleshooting. In order to solve the problem that the outlier anomaly data of the optical fiber network is very diffuse and the detection accuracy is not high, an outlier detection algorithm based on the frequency response peak search in optical fiber networks is proposed. Firstly, the amplitude-frequency response curve of feature distribution of outlier data in fiber network is constructed. The super-linear chaotic characteristics of discrete anomaly data are analyzed. Secondly, the frequency response characteristics of outlier anomaly data are extracted. Clustering Detection of Abnormal Data. Finally, the simulation test is carried out. The results show that the proposed method can detect outlier data in optical fiber networks with high accuracy and strong anti-interference ability.